Evidence Based Medicine on FHIR Implementation Guide
2.0.0-ballot - ballot
Evidence Based Medicine on FHIR Implementation Guide
2.0.0-ballot - ballot
Evidence Based Medicine on FHIR Implementation Guide, published by HL7 International / Clinical Decision Support. This guide is not an authorized publication; it is the continuous build for version 2.0.0-ballot built by the FHIR (HL7® FHIR® Standard) CI Build. This version is based on the current content of https://github.com/HL7/ebm/ and changes regularly. See the Directory of published versions
{
"resourceType" : "Evidence",
"id" : "179683",
"meta" : {
"versionId" : "20",
"lastUpdated" : "2024-11-16T18:46:30.134Z",
"profile" : [
🔗 "http://hl7.org/fhir/uv/ebm/StructureDefinition/endpoint-analysis-plan"
]
},
"text" : {
"status" : "extensions",
"div" : "<div xmlns=\"http://www.w3.org/1999/xhtml\"><p class=\"res-header-id\"><b>Generated Narrative: Evidence 179683</b></p><a name=\"179683\"> </a><a name=\"hc179683\"> </a><a name=\"179683-en-US\"> </a><div style=\"display: inline-block; background-color: #d9e0e7; padding: 6px; margin: 4px; border: 1px solid #8da1b4; border-radius: 5px; line-height: 60%\"><p style=\"margin-bottom: 0px\">version: 20; Last updated: 2024-11-16 18:46:30+0000</p><p style=\"margin-bottom: 0px\">Profile: <a href=\"StructureDefinition-endpoint-analysis-plan.html\">EndpointAnalysisPlan</a></p></div><p><b>url</b>: <a href=\"https://fevir.net/resources/Evidence/179683\">https://fevir.net/resources/Evidence/179683</a></p><p><b>identifier</b>: FEvIR Object Identifier/https://fevir.net/FOI/179683</p><p><b>name</b>: ADAS_Cog11_EndpointAnalysisPlan_from_PHUSE_Lilly_Redacted_Protocol_EBMonFHIR_IG_Version</p><p><b>title</b>: ADAS-Cog(11) EndpointAnalysisPlan from PHUSE Lilly Redacted Protocol - EBMonFHIR IG Version</p><p><b>status</b>: Active</p><p><b>publisher</b>: Computable Publishing LLC</p><p><b>contact</b>: <a href=\"mailto:support@computablepublishing.com\">support@computablepublishing.com</a></p><p><b>author</b>: Brian S. Alper: </p><h3>UseContexts</h3><table class=\"grid\"><tr><td style=\"display: none\">-</td><td><b>Code</b></td><td><b>Value[x]</b></td></tr><tr><td style=\"display: none\">*</td><td><a href=\"CodeSystem-179423.html#179423-evidence-communication\">Evidence Based Medicine on FHIR Implementation Guide Code System evidence-communication</a>: Evidence Communication</td><td><span title=\"Codes:{https://fevir.net/resources/CodeSystem/179423 EndpointAnalysisPlan}\">EndpointAnalysisPlan</span></td></tr></table><p><b>copyright</b>: </p><div><p>https://creativecommons.org/licenses/by-nc-sa/4.0/</p>\n</div><h3>RelatedArtifacts</h3><table class=\"grid\"><tr><td style=\"display: none\">-</td><td><b>Type</b></td><td><b>Display</b></td><td><b>Citation</b></td><td><b>ResourceReference</b></td></tr><tr><td style=\"display: none\">*</td><td>Cite As</td><td> </td><td><div><p>ADAS-Cog(11) EndpointAnalysisPlan from PHUSE Lilly Redacted Protocol - EBMonFHIR IG Version [Evidence]. Contributors: Brian S. Alper [Authors/Creators]. In: Fast Evidence Interoperability Resources (FEvIR) Platform, FOI 179683. Revised 2023-12-04. Available at: https://fevir.net/resources/Evidence/179683. Computable resource at: https://fevir.net/resources/Evidence/179683.</p>\n</div></td><td> </td></tr><tr><td style=\"display: none\">*</td><td>Supported With</td><td>Protocol attachment in associated Evidence Resource</td><td> </td><td><a href=\"Evidence-179691.html\">Example EndpointAnalysisPlan from PHUSE Lilly Redacted Protocol - EBMonFHIR IG Version</a></td></tr></table><p><b>description</b>: </p><div><p>An example of an EndpointAnalysisPlan Profile which uses intended='true' and include-if extensions within Evidence.statistic.modelCharacteristic elements.</p>\n</div><p><b>note</b>: Approximately 100 patients will be randomized to each of the 3 treatment groups (high dose, low dose, and placebo). Previous experience with the oral formulation of xanomeline suggests that this sample size has 90% power to detect a 3.0 mean treatment difference in ADAS-Cog (p<.05, twosided), based on a standard deviation of 6.5. \n\nGroup mean changes from baseline in the primary efficacy parameters will serve as efficacy criteria.\n\nThe primary analysis of efficacy will include only the data obtained up to and including the visit of discontinuation of study drug. Furthermore, the primary analysis will not include efficacy data obtained at any visit where the study drug was not administered in the preceding three days. Analyses that include the retrieved dropouts are considered secondary. In general, all patients will be included in all analyses of efficacy if they have a baseline measurement and at least one postrandomization measurement.\n\nThe primary analysis of ADAS-Cog (11) and CIBIC+ will be the 24-week endpoint, which is defined for each patient and variable as the last measurement obtained postrandomization (prior to protocol defined reduction in dose). a last-observation-carried-forward (LOCF). Note that the LOCF analysis at 24 weeks is the same as the endpoint analysis described previously. \n\nThe primary method to be used for the primary efficacy variables will be analysis of covariance (ANCOVA). Effects in the ANCOVA model will be the corresponding baseline score, investigator, and treatment. Investigator-by-treatment interaction will be tested in a full model prior to conducting the primary ANCOVA (see description below). Because 3 treatment groups are involved, the primary analysis will be the test for linear dose response in the ANCOVA model described in the preceding paragraph. The result is then a single p-value for ADAS-Cog. \n\nInvestigator-by-treatment interaction will be tested in a full ANCOVA or ANOVA model, which takes the models described above, and adds the interaction term to the model. Interaction will be tested at α = .10 level. When the interaction is significant at this level, the data will be examined for each individual investigator to attempt to identify the source of the significant interaction. When the interaction is not significant, this term will be dropped from the model as described above, to test for investigator and treatment main effects. By doing so, all ANCOVA and ANOVA models will be able to validly test for treatment differences without weighting each investigator equally, which is what occurs when using Type III sums of squares (cell means model) with the interaction term present in the model. This equal weighting of investigators can become a serious problem when sample sizes are dramatically different between investigators. \n\nFor all ANOVA and ANCOVA models, data collected from investigators who enrolled fewer than 3 patients in any one treatment group will be combined prior to analysis. If this combination still results in a treatment group having fewer than 3 patients in any one treatment group, then this group of patients will be combined with the next fewestenrolling investigator. In the event that there is a tie for fewest-enrolling investigator, one of these will be chosen at random by a random-number generator.\n\nThe inherent assumption of normally distributed data will be evaluated by generating output for the residuals from the full ANCOVA and ANOVA models, which include the interaction term, and by testing for normality using the Shapiro-Wilk test from PROC UNIVARIATE. In the event that the data are predominantly nonnormally distributed, analyses will also be conducted on the ranked data. This rank transformation will be applied by ranking all the data for a particular variable, across all investigators and treatments, from lowest to highest. Integer ranks will be assigned starting at 1; mean ranks will be assigned when ties occur. \n\nAll comparisons between xanomeline and placebo with respect to efficacy variables should be one-sided. The null hypothesis is that the drug is equal or worse than placebo. The alternative\nhypothesis is that the drug has greater efficacy than placebo. \n\nDifferent regulatory agencies require different type I error rates. Treatment differences that are significant at the .025 α-level will be declared to be “statistically significant.” When a computed p-value falls between .025 and .05, the differences will be described as “marginally statistically significant.” This approach satisfies regulatory agencies who have accepted a one-sided test at the .05 level, and other regulatory agencies who have requested a two-sided test at the .05 level, or equivalently, a one-sided test at the .025 level. In order to facilitate the review of the final study report, two-sided p-values will be presented in addition to the one-sided p-values.</p><blockquote><p><b>variableDefinition</b></p><p><b>description</b>: </p><div><p>high dose xanomeline vs. low dose xanomeline vs. placebo</p>\n</div><p><b>variableRole</b>: Exposure</p><p><b>comparatorCategory</b>: placebo</p><p><b>observed</b>: <a href=\"EvidenceVariable-179689.html\">GroupAssignment: high dose xanomeline vs. low dose xanomeline vs. placebo</a></p></blockquote><blockquote><p><b>variableDefinition</b></p><p><b>description</b>: </p><div><p>ADAS-Cog(11) at 24 weeks</p>\n</div><p><b>variableRole</b>: Outcome</p></blockquote><blockquote><p><b>statistic</b></p><p><b>statisticType</b>: <span title=\"Codes:{http://terminology.hl7.org/CodeSystem/statistic-type 0000457}\">(mean treatment difference)</span></p><blockquote><p><b>attributeEstimate</b></p><p><b>description</b>: </p><div><p>p value for one-sided test</p>\n</div><p><b>type</b>: <span title=\"Codes:{https://fevir.net/resources/CodeSystem/181513 TBD:p-value-one-sided}\">p value for one-sided test</span></p></blockquote><blockquote><p><b>attributeEstimate</b></p><p><b>description</b>: </p><div><p>p value for two-sided test</p>\n</div><p><b>type</b>: <span title=\"Codes:{https://fevir.net/resources/CodeSystem/181513 TBD:p-value-two-sided}\">p value for two-sided test</span></p></blockquote><blockquote><p><b>modelCharacteristic</b></p><p><b>code</b>: <span title=\"Codes:{https://fevir.net/resources/CodeSystem/181513 TBD:participant-inclusion-criteria-for-analysis}\">participant inclusion criteria for analysis</span></p><p><b>value</b>: <span title=\"Codes:\">In general, all patients will be included in all analyses of efficacy if they have a baseline measurement and at least one postrandomization measurement.</span></p><p><b>intended</b>: true</p></blockquote><blockquote><p><b>modelCharacteristic</b></p><p><b>code</b>: <span title=\"Codes:{https://fevir.net/resources/CodeSystem/181513 TBD:data-inclusion-criteria-for-analysis}\">data inclusion criteria for analysis</span></p><p><b>value</b>: <span title=\"Codes:{https://fevir.net/resources/CodeSystem/179423 defined-in-text}\">The primary analysis of efficacy will include only the data obtained up to and including the visit of discontinuation of study drug. Furthermore, the primary analysis will not include efficacy data obtained at any visit where the study drug was not administered in the preceding three days.</span></p><p><b>intended</b>: true</p></blockquote><blockquote><p><b>modelCharacteristic</b></p><p><b>code</b>: <span title=\"Codes:{https://fevir.net/resources/CodeSystem/181513 TBD:handling-of-missing-endpoint-data}\">handling of missing endpoint data</span></p><p><b>value</b>: <span title=\"Codes:{https://fevir.net/resources/CodeSystem/181513 TBD:single-imputation-by-LOCF}\">single imputation by last-observation-carried-forward (LOCF)</span></p><p><b>intended</b>: true</p></blockquote><blockquote><p><b>modelCharacteristic</b></p><p><b>code</b>: <span title=\"Codes:{https://fevir.net/resources/CodeSystem/181513 TBD:data-inclusion-criteria-for-secondary-analysis}\">data inclusion criteria for secondary analysis</span></p><p><b>value</b>: <span title=\"Codes:{https://fevir.net/resources/CodeSystem/179423 defined-in-text}\">The primary analysis of efficacy will include only the data obtained up to and including the visit of discontinuation of study drug. Furthermore, the primary analysis will not include efficacy data obtained at any visit where the study drug was not administered in the preceding three days. Analyses that include the retrieved dropouts are considered secondary.</span></p><p><b>intended</b>: true</p></blockquote><blockquote><p><b>modelCharacteristic</b></p><p><b>code</b>: <span title=\"Codes:{https://fevir.net/resources/CodeSystem/181513 STATO:0000286}\">one-tailed test</span></p><p><b>intended</b>: true</p></blockquote><blockquote><p><b>modelCharacteristic</b></p><p><b>code</b>: <span title=\"Codes:{https://fevir.net/resources/CodeSystem/181513 TBD:0000081}\">alpha setting</span></p><p><b>value</b>: 0.025</p><p><b>intended</b>: true</p></blockquote><blockquote><p><b>modelCharacteristic</b></p><p><b>code</b>: <span title=\"Codes:{https://fevir.net/resources/CodeSystem/179423 defined-in-text}\">threshold for marginal statistical significance</span></p><p><b>value</b>: 0.025-0.05</p><p><b>intended</b>: true</p></blockquote><blockquote><p><b>modelCharacteristic</b></p><p><b>code</b>: <span title=\"Codes:{https://fevir.net/resources/CodeSystem/181513 TBD:null-hypothesis}\">null hypothesis</span></p><p><b>value</b>: <span title=\"Codes:{https://fevir.net/resources/CodeSystem/179423 defined-in-text}\">xanomeline is equal or worse than placebo</span></p><p><b>intended</b>: true</p></blockquote><blockquote><p><b>modelCharacteristic</b></p><p><b>code</b>: <span title=\"Codes:{https://fevir.net/resources/CodeSystem/181513 TBD:alternative-hypothesis}\">alternative hypothesis</span></p><p><b>value</b>: <span title=\"Codes:{https://fevir.net/resources/CodeSystem/179423 defined-in-text}\">xanomeline has greater efficacy than placebo</span></p><p><b>intended</b>: true</p></blockquote><blockquote><p><b>modelCharacteristic</b></p><p><b>code</b>: <span title=\"Codes:{https://fevir.net/resources/CodeSystem/181513 TBD:statistical-software-package}\">statistical software package</span></p><p><b>value</b>: <span title=\"Codes:{https://fevir.net/resources/CodeSystem/179423 defined-in-text}\">SAS</span></p><p><b>intended</b>: true</p></blockquote><blockquote><p><b>modelCharacteristic</b></p><p><b>code</b>: <span title=\"Codes:{https://fevir.net/resources/CodeSystem/181513 TBD:sample-size}\">Sample Size/Power Calculation ~ 90% power to detect a 3.0 mean treatment difference in ADAS-Cog (p<.05, twosided), based on a standard deviation of 6.5 and sample size of 100 patients in each of 3 groups</span></p><p><b>intended</b>: true</p><blockquote><p><b>attribute</b></p><p><b>description</b>: </p><div><p>90% power</p>\n</div><p><b>type</b>: <span title=\"Codes:{https://fevir.net/resources/CodeSystem/181513 TBD:power}\">power</span></p><p><b>quantity</b>: 90 %<span style=\"background: LightGoldenRodYellow\"> (Details: UCUM code% = '%')</span></p></blockquote><blockquote><p><b>attribute</b></p><p><b>description</b>: </p><div><p>minimally detectable threshold value 3.0</p>\n</div><p><b>type</b>: <span title=\"Codes:{https://fevir.net/resources/CodeSystem/181513 TBD:checkIfInSTATOtesting-margin}\">minimally detectable threshold value</span></p><p><b>quantity</b>: 3</p></blockquote><blockquote><p><b>attribute</b></p><p><b>description</b>: </p><div><p>p<.05</p>\n</div><p><b>type</b>: <span title=\"Codes:{https://fevir.net/resources/CodeSystem/181513 TBD:0000081}\">alpha setting</span></p><p><b>quantity</b>: 0.05</p></blockquote><blockquote><p><b>attribute</b></p><p><b>description</b>: </p><div><p>standard deviation of 6.5</p>\n</div><p><b>type</b>: <span title=\"Codes:{https://fevir.net/resources/CodeSystem/181513 STATO:0000237}\">Standard deviation</span></p><p><b>quantity</b>: 6.5</p></blockquote><blockquote><p><b>attribute</b></p><p><b>description</b>: </p><div><p>sample size of 100 patients in each of 3 groups</p>\n</div><p><b>type</b>: <span title=\"Codes:{https://fevir.net/resources/CodeSystem/181513 TBD:sample-size-per-group}\">sample size per group</span></p><p><b>quantity</b>: 100</p></blockquote><blockquote><p><b>attribute</b></p><p><b>description</b>: </p><div><p>two-tailed test</p>\n</div><p><b>type</b>: <span title=\"Codes:{https://fevir.net/resources/CodeSystem/181513 STATO:0000287}\">two-tailed test</span></p></blockquote><blockquote><p><b>attribute</b></p><p><b>description</b>: </p><div><p>sample permutation testing - Because there will be roughly 300!/(3 * 100!) possible permutations of the data, random data permutations will be sampled (10,000 random permutations). -- distribution assumption for comparison if random</p>\n</div><p><b>type</b>: <span title=\"Codes:{https://fevir.net/resources/CodeSystem/181513 TBD:prospective-sample-permutation-testing}\">prospective sample permutation testing</span></p><h3>AttributeEstimates</h3><table class=\"grid\"><tr><td style=\"display: none\">-</td><td><b>Type</b></td><td><b>Quantity</b></td></tr><tr><td style=\"display: none\">*</td><td><span title=\"Codes:{https://fevir.net/resources/CodeSystem/181513 TBD:number-of-permutations-sampled}\">number of permutations sampled</span></td><td>10000</td></tr><tr><td style=\"display: none\">*</td><td><span title=\"Codes:{https://fevir.net/resources/CodeSystem/179423 defined-in-text}\">allocation ratio 1:1:1</span></td><td> </td></tr></table></blockquote></blockquote><blockquote><p><b>modelCharacteristic</b></p><p><b>code</b>: <span title=\"Codes:{https://fevir.net/resources/CodeSystem/181513 TBD:primary-analytic-method}\">Primary analytic method</span></p><p><b>value</b>: <span title=\"Codes:{https://fevir.net/resources/CodeSystem/181513 TBD:ANCOVA}\">analysis of covariance (ANCOVA)</span></p><p><b>intended</b>: true</p><blockquote><p><b>variable</b></p><p><b>variableDefinition</b>: baseline ADAS-Cog(11) score</p><p><b>handling</b>: continuous variable</p></blockquote><blockquote><p><b>variable</b></p><p><b>variableDefinition</b>: <a href=\"EvidenceVariable-159673.html\">investigator</a></p><p><b>handling</b>: polychotomous variable</p></blockquote><blockquote><p><b>variable</b></p><p><b>variableDefinition</b>: treatment</p><p><b>handling</b>: ordinal variable</p><p><b>valueCategory</b>: <span title=\"Codes:\">high dose xanomeline</span>, <span title=\"Codes:\">low dose xanomeline</span>, <span title=\"Codes:\">placebo</span></p></blockquote><blockquote><p><b>variable</b></p><blockquote><p><b>StatisticModelIncludeIf</b></p><ul><li>attribute: <span title=\"Codes:\">p value for F test</span></li><li>value: <0.1</li></ul></blockquote><p><b>variableDefinition</b>: <a href=\"EvidenceVariable-156673.html\">Investigator-by-treatment interaction</a></p><p><b>handling</b>: polychotomous variable</p></blockquote></blockquote><blockquote><p><b>modelCharacteristic</b></p><blockquote><p><b>StatisticModelIncludeIf</b></p><ul><li>attribute: <span title=\"Codes:\">Defined by Expression</span></li><li>value: <span title=\"TBD-rewrite in CQL or FHIRPath\"><code>Evidence[id='156984'].statistic[statisticType='F test'].attributeEstimate[type='p value'].quantity < 0.1</code></span>("When the Investigator-by-treatment interaction (p value for F test) is significant at the 0.1 level")</li></ul></blockquote><p><b>code</b>: <span title=\"Codes:{https://fevir.net/resources/CodeSystem/179423 defined-in-text}\">additional investigation</span></p><p><b>value</b>: <span title=\"Codes:{https://fevir.net/resources/CodeSystem/181513 TBD:identify-source-of-interaction}\">the data will be examined for each individual investigator [EvidenceVariable/159673] to attempt to identify the source of the significant interaction.</span></p><p><b>intended</b>: true</p><h3>Variables</h3><table class=\"grid\"><tr><td style=\"display: none\">-</td><td><b>VariableDefinition</b></td><td><b>Handling</b></td></tr><tr><td style=\"display: none\">*</td><td><a href=\"EvidenceVariable-159673.html\">investigator</a></td><td>polychotomous variable</td></tr></table></blockquote><blockquote><p><b>modelCharacteristic</b></p><blockquote><p><b>StatisticModelIncludeIf</b></p><ul><li>attribute: <span title=\"Codes:\">Defined by Expression</span></li><li>value: <span title=\"TBD-rewrite in CQL or FHIRPath\"><code>(Evidence[id='168845'].statistic[statisticType='Shapiro-Wilk test'].attributeEstimate[type='p value'].quantity < 0.05), using SAS PROC UNIVARIATE</code></span>("residuals are nonnormally distributed using the Shapiro-Wilk test from PROC UNIVARIATE")</li></ul></blockquote><p><b>code</b>: <span title=\"Codes:{https://fevir.net/resources/CodeSystem/181513 TBD:rank-based-analytic-method}\">rank-based analytic method</span></p><p><b>value</b>: <span title=\"Codes:\">Analyses will also be conducted on the ranked data. This rank transformation will be applied by ranking all the data for a particular variable, across all investigators and treatments, from lowest to highest. Integer ranks will be assigned starting at 1; mean ranks will be assigned when ties occur..</span></p><p><b>intended</b>: true</p></blockquote></blockquote></div>"
},
"url" : "https://fevir.net/resources/Evidence/179683",
"identifier" : [
{
"type" : {
"coding" : [
{
"system" : "http://terminology.hl7.org/CodeSystem/v2-0203",
"code" : "ACSN",
"display" : "Accession ID"
}
],
"text" : "FEvIR Object Identifier"
},
"system" : "urn:ietf:rfc:3986",
"value" : "https://fevir.net/FOI/179683",
"assigner" : {
"display" : "Computable Publishing LLC"
}
}
],
"name" : "ADAS_Cog11_EndpointAnalysisPlan_from_PHUSE_Lilly_Redacted_Protocol_EBMonFHIR_IG_Version",
"title" : "ADAS-Cog(11) EndpointAnalysisPlan from PHUSE Lilly Redacted Protocol - EBMonFHIR IG Version",
"status" : "active",
"publisher" : "Computable Publishing LLC",
"contact" : [
{
"telecom" : [
{
"system" : "email",
"value" : "support@computablepublishing.com"
}
]
}
],
"author" : [
{
"name" : "Brian S. Alper"
}
],
"useContext" : [
{
"code" : {
"system" : "https://fevir.net/resources/CodeSystem/179423",
"code" : "evidence-communication",
"display" : "Evidence Communication"
},
"valueCodeableConcept" : {
"coding" : [
{
"system" : "https://fevir.net/resources/CodeSystem/179423",
"code" : "EndpointAnalysisPlan",
"display" : "EndpointAnalysisPlan"
}
]
}
}
],
"copyright" : "https://creativecommons.org/licenses/by-nc-sa/4.0/",
"relatedArtifact" : [
{
"type" : "cite-as",
"citation" : "ADAS-Cog(11) EndpointAnalysisPlan from PHUSE Lilly Redacted Protocol - EBMonFHIR IG Version [Evidence]. Contributors: Brian S. Alper [Authors/Creators]. In: Fast Evidence Interoperability Resources (FEvIR) Platform, FOI 179683. Revised 2023-12-04. Available at: https://fevir.net/resources/Evidence/179683. Computable resource at: https://fevir.net/resources/Evidence/179683."
},
{
"type" : "supported-with",
"display" : "Protocol attachment in associated Evidence Resource",
"resourceReference" : {
🔗 "reference" : "Evidence/179691",
"type" : "Evidence",
"display" : "Example EndpointAnalysisPlan from PHUSE Lilly Redacted Protocol - EBMonFHIR IG Version"
}
}
],
"description" : "An example of an EndpointAnalysisPlan Profile which uses intended='true' and include-if extensions within Evidence.statistic.modelCharacteristic elements.",
"note" : [
{
"text" : "Approximately 100 patients will be randomized to each of the 3 treatment groups (high dose, low dose, and placebo). Previous experience with the oral formulation of xanomeline suggests that this sample size has 90% power to detect a 3.0 mean treatment difference in ADAS-Cog (p<.05, twosided), based on a standard deviation of 6.5. \n\nGroup mean changes from baseline in the primary efficacy parameters will serve as efficacy criteria.\n\nThe primary analysis of efficacy will include only the data obtained up to and including the visit of discontinuation of study drug. Furthermore, the primary analysis will not include efficacy data obtained at any visit where the study drug was not administered in the preceding three days. Analyses that include the retrieved dropouts are considered secondary. In general, all patients will be included in all analyses of efficacy if they have a baseline measurement and at least one postrandomization measurement.\n\nThe primary analysis of ADAS-Cog (11) and CIBIC+ will be the 24-week endpoint, which is defined for each patient and variable as the last measurement obtained postrandomization (prior to protocol defined reduction in dose). a last-observation-carried-forward (LOCF). Note that the LOCF analysis at 24 weeks is the same as the endpoint analysis described previously. \n\nThe primary method to be used for the primary efficacy variables will be analysis of covariance (ANCOVA). Effects in the ANCOVA model will be the corresponding baseline score, investigator, and treatment. Investigator-by-treatment interaction will be tested in a full model prior to conducting the primary ANCOVA (see description below). Because 3 treatment groups are involved, the primary analysis will be the test for linear dose response in the ANCOVA model described in the preceding paragraph. The result is then a single p-value for ADAS-Cog. \n\nInvestigator-by-treatment interaction will be tested in a full ANCOVA or ANOVA model, which takes the models described above, and adds the interaction term to the model. Interaction will be tested at α = .10 level. When the interaction is significant at this level, the data will be examined for each individual investigator to attempt to identify the source of the significant interaction. When the interaction is not significant, this term will be dropped from the model as described above, to test for investigator and treatment main effects. By doing so, all ANCOVA and ANOVA models will be able to validly test for treatment differences without weighting each investigator equally, which is what occurs when using Type III sums of squares (cell means model) with the interaction term present in the model. This equal weighting of investigators can become a serious problem when sample sizes are dramatically different between investigators. \n\nFor all ANOVA and ANCOVA models, data collected from investigators who enrolled fewer than 3 patients in any one treatment group will be combined prior to analysis. If this combination still results in a treatment group having fewer than 3 patients in any one treatment group, then this group of patients will be combined with the next fewestenrolling investigator. In the event that there is a tie for fewest-enrolling investigator, one of these will be chosen at random by a random-number generator.\n\nThe inherent assumption of normally distributed data will be evaluated by generating output for the residuals from the full ANCOVA and ANOVA models, which include the interaction term, and by testing for normality using the Shapiro-Wilk test from PROC UNIVARIATE. In the event that the data are predominantly nonnormally distributed, analyses will also be conducted on the ranked data. This rank transformation will be applied by ranking all the data for a particular variable, across all investigators and treatments, from lowest to highest. Integer ranks will be assigned starting at 1; mean ranks will be assigned when ties occur. \n\nAll comparisons between xanomeline and placebo with respect to efficacy variables should be one-sided. The null hypothesis is that the drug is equal or worse than placebo. The alternative\nhypothesis is that the drug has greater efficacy than placebo. \n\nDifferent regulatory agencies require different type I error rates. Treatment differences that are significant at the .025 α-level will be declared to be “statistically significant.” When a computed p-value falls between .025 and .05, the differences will be described as “marginally statistically significant.” This approach satisfies regulatory agencies who have accepted a one-sided test at the .05 level, and other regulatory agencies who have requested a two-sided test at the .05 level, or equivalently, a one-sided test at the .025 level. In order to facilitate the review of the final study report, two-sided p-values will be presented in addition to the one-sided p-values."
}
],
"variableDefinition" : [
{
"description" : "high dose xanomeline vs. low dose xanomeline vs. placebo",
"variableRole" : "exposure",
"comparatorCategory" : "placebo",
"observed" : {
🔗 "reference" : "EvidenceVariable/179689",
"type" : "EvidenceVariable",
"display" : "GroupAssignment: high dose xanomeline vs. low dose xanomeline vs. placebo"
}
},
{
"description" : "ADAS-Cog(11) at 24 weeks",
"variableRole" : "outcome"
}
],
"statistic" : [
{
"statisticType" : {
"coding" : [
{
"system" : "http://terminology.hl7.org/CodeSystem/statistic-type",
"code" : "0000457",
"display" : "Mean Difference"
}
],
"text" : "(mean treatment difference)"
},
"attributeEstimate" : [
{
"description" : "p value for one-sided test",
"type" : {
"coding" : [
{
"system" : "https://fevir.net/resources/CodeSystem/181513",
"code" : "TBD:p-value-one-sided",
"display" : "p value for one-sided test"
}
],
"text" : "p value for one-sided test"
}
},
{
"description" : "p value for two-sided test",
"type" : {
"coding" : [
{
"system" : "https://fevir.net/resources/CodeSystem/181513",
"code" : "TBD:p-value-two-sided",
"display" : "p value for two-sided test"
}
],
"text" : "p value for two-sided test"
}
}
],
"modelCharacteristic" : [
{
"code" : {
"coding" : [
{
"system" : "https://fevir.net/resources/CodeSystem/181513",
"code" : "TBD:participant-inclusion-criteria-for-analysis",
"display" : "participant inclusion criteria for analysis"
}
],
"text" : "participant inclusion criteria for analysis"
},
"valueCodeableConcept" : {
"text" : "In general, all patients will be included in all analyses of efficacy if they have a baseline measurement and at least one postrandomization measurement."
},
"intended" : true
},
{
"code" : {
"coding" : [
{
"system" : "https://fevir.net/resources/CodeSystem/181513",
"code" : "TBD:data-inclusion-criteria-for-analysis",
"display" : "data inclusion criteria for analysis"
}
],
"text" : "data inclusion criteria for analysis"
},
"valueCodeableConcept" : {
"coding" : [
{
"system" : "https://fevir.net/resources/CodeSystem/179423",
"code" : "defined-in-text",
"display" : "defined in text"
}
],
"text" : "The primary analysis of efficacy will include only the data obtained up to and including the visit of discontinuation of study drug. Furthermore, the primary analysis will not include efficacy data obtained at any visit where the study drug was not administered in the preceding three days."
},
"intended" : true
},
{
"code" : {
"coding" : [
{
"system" : "https://fevir.net/resources/CodeSystem/181513",
"code" : "TBD:handling-of-missing-endpoint-data",
"display" : "handling of missing endpoint data"
}
],
"text" : "handling of missing endpoint data"
},
"valueCodeableConcept" : {
"coding" : [
{
"system" : "https://fevir.net/resources/CodeSystem/181513",
"code" : "TBD:single-imputation-by-LOCF",
"display" : "single imputation by last-observation-carried-forward (LOCF)"
}
],
"text" : "single imputation by last-observation-carried-forward (LOCF)"
},
"intended" : true
},
{
"code" : {
"coding" : [
{
"system" : "https://fevir.net/resources/CodeSystem/181513",
"code" : "TBD:data-inclusion-criteria-for-secondary-analysis",
"display" : "data inclusion criteria for secondary analysis"
}
],
"text" : "data inclusion criteria for secondary analysis"
},
"valueCodeableConcept" : {
"coding" : [
{
"system" : "https://fevir.net/resources/CodeSystem/179423",
"code" : "defined-in-text",
"display" : "defined in text"
}
],
"text" : "The primary analysis of efficacy will include only the data obtained up to and including the visit of discontinuation of study drug. Furthermore, the primary analysis will not include efficacy data obtained at any visit where the study drug was not administered in the preceding three days. Analyses that include the retrieved dropouts are considered secondary."
},
"intended" : true
},
{
"code" : {
"coding" : [
{
"system" : "https://fevir.net/resources/CodeSystem/181513",
"code" : "STATO:0000286",
"display" : "one-tailed test"
}
]
},
"intended" : true
},
{
"code" : {
"coding" : [
{
"system" : "https://fevir.net/resources/CodeSystem/181513",
"code" : "TBD:0000081",
"display" : "alpha setting"
}
]
},
"valueQuantity" : {
"value" : 0.025
},
"intended" : true
},
{
"code" : {
"coding" : [
{
"system" : "https://fevir.net/resources/CodeSystem/179423",
"code" : "defined-in-text",
"display" : "defined in text"
}
],
"text" : "threshold for marginal statistical significance"
},
"valueRange" : {
"low" : {
"value" : 0.025
},
"high" : {
"value" : 0.05
}
},
"intended" : true
},
{
"code" : {
"coding" : [
{
"system" : "https://fevir.net/resources/CodeSystem/181513",
"code" : "TBD:null-hypothesis",
"display" : "null hypothesis"
}
],
"text" : "null hypothesis"
},
"valueCodeableConcept" : {
"coding" : [
{
"system" : "https://fevir.net/resources/CodeSystem/179423",
"code" : "defined-in-text",
"display" : "defined in text"
}
],
"text" : "xanomeline is equal or worse than placebo"
},
"intended" : true
},
{
"code" : {
"coding" : [
{
"system" : "https://fevir.net/resources/CodeSystem/181513",
"code" : "TBD:alternative-hypothesis",
"display" : "alternative hypothesis"
}
],
"text" : "alternative hypothesis"
},
"valueCodeableConcept" : {
"coding" : [
{
"system" : "https://fevir.net/resources/CodeSystem/179423",
"code" : "defined-in-text",
"display" : "defined in text"
}
],
"text" : "xanomeline has greater efficacy than placebo"
},
"intended" : true
},
{
"code" : {
"coding" : [
{
"system" : "https://fevir.net/resources/CodeSystem/181513",
"code" : "TBD:statistical-software-package",
"display" : "statistical software package"
}
],
"text" : "statistical software package"
},
"valueCodeableConcept" : {
"coding" : [
{
"system" : "https://fevir.net/resources/CodeSystem/179423",
"code" : "defined-in-text",
"display" : "defined in text"
}
],
"text" : "SAS"
},
"intended" : true
},
{
"code" : {
"coding" : [
{
"system" : "https://fevir.net/resources/CodeSystem/181513",
"code" : "TBD:sample-size",
"display" : "Sample size estimation"
}
],
"text" : "Sample Size/Power Calculation ~ 90% power to detect a 3.0 mean treatment difference in ADAS-Cog (p<.05, twosided), based on a standard deviation of 6.5 and sample size of 100 patients in each of 3 groups"
},
"intended" : true,
"attribute" : [
{
"description" : "90% power",
"type" : {
"coding" : [
{
"system" : "https://fevir.net/resources/CodeSystem/181513",
"code" : "TBD:power",
"display" : "Power"
}
],
"text" : "power"
},
"quantity" : {
"value" : 90,
"unit" : "%",
"system" : "http://unitsofmeasure.org",
"code" : "%"
}
},
{
"description" : "minimally detectable threshold value 3.0",
"type" : {
"coding" : [
{
"system" : "https://fevir.net/resources/CodeSystem/181513",
"code" : "TBD:checkIfInSTATOtesting-margin",
"display" : "Hypothesis testing margin"
}
],
"text" : "minimally detectable threshold value"
},
"quantity" : {
"value" : 3
}
},
{
"description" : "p<.05",
"type" : {
"coding" : [
{
"system" : "https://fevir.net/resources/CodeSystem/181513",
"code" : "TBD:0000081",
"display" : "alpha setting"
}
]
},
"quantity" : {
"value" : 0.05
}
},
{
"description" : "standard deviation of 6.5",
"type" : {
"coding" : [
{
"system" : "https://fevir.net/resources/CodeSystem/181513",
"code" : "STATO:0000237",
"display" : "Standard deviation"
}
]
},
"quantity" : {
"value" : 6.5
}
},
{
"description" : "sample size of 100 patients in each of 3 groups",
"type" : {
"coding" : [
{
"system" : "https://fevir.net/resources/CodeSystem/181513",
"code" : "TBD:sample-size-per-group",
"display" : "sample size per group"
}
]
},
"quantity" : {
"value" : 100
}
},
{
"description" : "two-tailed test",
"type" : {
"coding" : [
{
"system" : "https://fevir.net/resources/CodeSystem/181513",
"code" : "STATO:0000287",
"display" : "two-tailed test"
}
]
}
},
{
"description" : "sample permutation testing - Because there will be roughly 300!/(3 * 100!) possible permutations of the data, random data permutations will be sampled (10,000 random permutations). -- distribution assumption for comparison if random",
"type" : {
"coding" : [
{
"system" : "https://fevir.net/resources/CodeSystem/181513",
"code" : "TBD:prospective-sample-permutation-testing",
"display" : "prospective sample permutation testing"
}
],
"text" : "prospective sample permutation testing"
},
"attributeEstimate" : [
{
"type" : {
"coding" : [
{
"system" : "https://fevir.net/resources/CodeSystem/181513",
"code" : "TBD:number-of-permutations-sampled",
"display" : "number of permutations sampled"
}
],
"text" : "number of permutations sampled"
},
"quantity" : {
"value" : 10000
}
},
{
"type" : {
"coding" : [
{
"system" : "https://fevir.net/resources/CodeSystem/179423",
"code" : "defined-in-text",
"display" : "defined in text"
}
],
"text" : "allocation ratio 1:1:1"
}
}
]
}
]
},
{
"code" : {
"coding" : [
{
"system" : "https://fevir.net/resources/CodeSystem/181513",
"code" : "TBD:primary-analytic-method",
"display" : "primary analytic method"
}
],
"text" : "Primary analytic method"
},
"valueCodeableConcept" : {
"coding" : [
{
"system" : "https://fevir.net/resources/CodeSystem/181513",
"code" : "TBD:ANCOVA",
"display" : "ANCOVA"
}
],
"text" : "analysis of covariance (ANCOVA)"
},
"intended" : true,
"variable" : [
{
"variableDefinition" : {
"display" : "baseline ADAS-Cog(11) score"
},
"handling" : "continuous"
},
{
"variableDefinition" : {
🔗 "reference" : "EvidenceVariable/159673",
"type" : "EvidenceVariable",
"display" : "investigator"
},
"handling" : "polychotomous"
},
{
"variableDefinition" : {
"display" : "treatment"
},
"handling" : "ordinal",
"valueCategory" : [
{
"text" : "high dose xanomeline"
},
{
"text" : "low dose xanomeline"
},
{
"text" : "placebo"
}
]
},
{
"extension" : [
{
"extension" : [
{
"url" : "attribute",
"valueCodeableConcept" : {
"text" : "p value for F test"
}
},
{
"url" : "value",
"valueQuantity" : {
"value" : 0.1,
"comparator" : "<"
}
}
],
"url" : "http://hl7.org/fhir/uv/ebm/StructureDefinition/statistic-model-include-if"
}
],
"variableDefinition" : {
🔗 "reference" : "EvidenceVariable/156673",
"type" : "EvidenceVariable",
"display" : "Investigator-by-treatment interaction"
},
"handling" : "polychotomous"
}
]
},
{
"extension" : [
{
"extension" : [
{
"url" : "attribute",
"valueCodeableConcept" : {
"text" : "Defined by Expression"
}
},
{
"url" : "value",
"valueExpression" : {
"description" : "When the Investigator-by-treatment interaction (p value for F test) is significant at the 0.1 level",
"language" : "TBD-rewrite in CQL or FHIRPath",
"expression" : "Evidence[id='156984'].statistic[statisticType='F test'].attributeEstimate[type='p value'].quantity < 0.1"
}
}
],
"url" : "http://hl7.org/fhir/uv/ebm/StructureDefinition/statistic-model-include-if"
}
],
"code" : {
"coding" : [
{
"system" : "https://fevir.net/resources/CodeSystem/179423",
"code" : "defined-in-text",
"display" : "defined in text"
}
],
"text" : "additional investigation"
},
"valueCodeableConcept" : {
"coding" : [
{
"system" : "https://fevir.net/resources/CodeSystem/181513",
"code" : "TBD:identify-source-of-interaction",
"display" : "identify source(s) of significant interaction"
}
],
"text" : "the data will be examined for each individual investigator [EvidenceVariable/159673] to attempt to identify the source of the significant interaction."
},
"intended" : true,
"variable" : [
{
"variableDefinition" : {
🔗 "reference" : "EvidenceVariable/159673",
"type" : "EvidenceVariable",
"display" : "investigator"
},
"handling" : "polychotomous"
}
]
},
{
"extension" : [
{
"extension" : [
{
"url" : "attribute",
"valueCodeableConcept" : {
"text" : "Defined by Expression"
}
},
{
"url" : "value",
"valueExpression" : {
"description" : "residuals are nonnormally distributed using the Shapiro-Wilk test from PROC UNIVARIATE",
"language" : "TBD-rewrite in CQL or FHIRPath",
"expression" : "(Evidence[id='168845'].statistic[statisticType='Shapiro-Wilk test'].attributeEstimate[type='p value'].quantity < 0.05), using SAS PROC UNIVARIATE"
}
}
],
"url" : "http://hl7.org/fhir/uv/ebm/StructureDefinition/statistic-model-include-if"
}
],
"code" : {
"coding" : [
{
"system" : "https://fevir.net/resources/CodeSystem/181513",
"code" : "TBD:rank-based-analytic-method",
"display" : "rank-based analytic method"
}
]
},
"valueCodeableConcept" : {
"text" : "Analyses will also be conducted on the ranked data. This rank transformation will be applied by ranking all the data for a particular variable, across all investigators and treatments, from lowest to highest. Integer ranks will be assigned starting at 1; mean ranks will be assigned when ties occur.."
},
"intended" : true
}
]
}
]
}
IG © 2024+ HL7 International / Clinical Decision Support. Package hl7.fhir.uv.ebm#2.0.0-ballot based on FHIR 6.0.0-ballot2. Generated 2024-11-21
Links: Table of Contents |
QA Report
| Version History |
|
Propose a change